Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, it discloses significant behavior: the invoice number is assigned at that moment so the invoice stops being a concept (irreversible state change), sending reaches external people and requires a customer email, a UBL file is attached, and per-call confirmation is default-on but switchable. This is rich, actionable context for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and the size is reasonable, but the confirmation guidance is split across two overlapping sentences ('By default you confirm each call...' and 'Reaches other people: confirm with the user before each call'), which is slight redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still covers the state transition, numbering, email/UBL requirements, external reach, confirmation policy, and the Cotlet API key requirement. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds precondition semantics for the send action ('needs the customer email address on the card') that the schema does not state, plus context on the default email text behavior. This meaningfully enriches understanding of the action parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: it 'emails a concept invoice to the customer or saves it without sending,' and adds that this finalizes the concept by assigning an invoice number. This is clearly distinguishable from create_sales_invoice, get_sales_invoice, and list_sales_invoices among its siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It describes the two modes and their conditions (send requires the customer email on the card and attaches a UBL file; save_only skips email), and notes it applies at step 4 of the invoice flow. It gives clear context but does not explicitly name alternative tools or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.